Multi-Variate Time Series Forecasting on Variable Subsets

TL;DR

This paper introduces Variable Subset Forecast (VSF), a new task in multivariate time series forecasting where only a subset of variables is available during inference, and proposes a technique to maintain high performance despite variable loss.

Contribution

The paper formulates the VSF task, highlights the robustness gap in existing models, and proposes a non-parametric wrapper method that significantly improves performance with limited variables.

Findings

State-of-the-art models degrade under variable loss

Proposed method recovers up to 95% of full-model performance

Technique is effective across multiple datasets and models

Abstract

We formulate a new inference task in the domain of multivariate time series forecasting (MTSF), called Variable Subset Forecast (VSF), where only a small subset of the variables is available during inference. Variables are absent during inference because of long-term data loss (eg. sensor failures) or high -> low-resource domain shift between train / test. To the best of our knowledge, robustness of MTSF models in presence of such failures, has not been studied in the literature. Through extensive evaluation, we first show that the performance of state of the art methods degrade significantly in the VSF setting. We propose a non-parametric, wrapper technique that can be applied on top any existing forecast models. Through systematic experiments across 4 datasets and 5 forecast models, we show that our technique is able to recover close to 95\% performance of the models even when only 15\% of the original variables are present.